AI alignment aims to make AI systems behave in line with human intentions and values. As
AI systems grow more capable, so do risks from misalignment. To provide a comprehensive …

The concepts of risk aversion, chance-constrained optimization, and robust optimization
have developed significantly over the last decade. The statistical learning community has …

Traditional machine learning paradigms are based on the assumption that both training and
test data follow the same statistical pattern, which is mathematically referred to as …

Learning models that gracefully handle distribution shifts is central to research on domain
generalization, robust optimization, and fairness. A promising formulation is domain …

Abstract Machine learning models (eg, speech recognizers) trained on average loss suffer
from representation disparity—minority groups (eg, non-native speakers) carry less weight in …

Neural networks are vulnerable to adversarial examples and researchers have proposed
many heuristic attack and defense mechanisms. We address this problem through the …

Learning models with uniform performance via distributionally robust optimization Page 1 The
Annals of Statistics 2021, Vol. 49, No. 3, 1378–1406 https://doi.org/10.1214/20-AOS2004 © …

As NLP models achieved state-of-the-art performances over benchmarks and gained wide
applications, it has been increasingly important to ensure the safe deployment of these …

The standard risk minimization paradigm of machine learning is brittle when operating in
environments whose test distributions are different from the training distribution due to …

We develop an approach to risk minimization and stochastic optimization that provides a
convex surrogate for variance, allowing near-optimal and computationally efficient trading …